{"id":18323274,"url":"https://github.com/camara94/natural-language-processing-tensorflow","last_synced_at":"2025-10-23T22:59:54.715Z","repository":{"id":100386467,"uuid":"477493173","full_name":"camara94/natural-language-processing-tensorflow","owner":"camara94","description":"Natural Language processing in tensorflow","archived":false,"fork":false,"pushed_at":"2022-04-11T06:38:37.000Z","size":30175,"stargazers_count":10,"open_issues_count":0,"forks_count":7,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-03-21T13:45:18.641Z","etag":null,"topics":["dataset","deep-learning","lstm-neural-networks","lstm-sentiment-analysis","machine-learning","natural-language-processing","nlp","nlp-keywords-extraction","nlp-machine-learning","rnn","rnn-tensorflow","sentiment-analysis","tensorflow","text-classification"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/camara94.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2022-04-03T23:38:27.000Z","updated_at":"2025-01-29T06:16:55.000Z","dependencies_parsed_at":"2023-05-14T07:30:25.690Z","dependency_job_id":null,"html_url":"https://github.com/camara94/natural-language-processing-tensorflow","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/camara94%2Fnatural-language-processing-tensorflow","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/camara94%2Fnatural-language-processing-tensorflow/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/camara94%2Fnatural-language-processing-tensorflow/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/camara94%2Fnatural-language-processing-tensorflow/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/camara94","download_url":"https://codeload.github.com/camara94/natural-language-processing-tensorflow/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247415783,"owners_count":20935383,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["dataset","deep-learning","lstm-neural-networks","lstm-sentiment-analysis","machine-learning","natural-language-processing","nlp","nlp-keywords-extraction","nlp-machine-learning","rnn","rnn-tensorflow","sentiment-analysis","tensorflow","text-classification"],"created_at":"2024-11-05T18:27:46.607Z","updated_at":"2025-10-23T22:59:54.711Z","avatar_url":"https://github.com/camara94.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# natural-language-processing-tensorflow\nNatural Language processing in tensorflow\n\n## Word Encoding\n\n![image](images/2.png)\n\n## Same With ASCI CODE\n\nWith asci analysis the word **LISTEN** and *SILENT** are the same value but the two words are very differents of meaning.\n![image](images/3.png)\n\n## How Sentiment Analysis Work\n\n![image](images/4.png)\n\n* How we can observed the similarity between two words\n\n![image](images/5.png)\n\n* Now if we look at the two sentences to determine the difference between two sentences.\n\n![image](images/6.png)\n\n\n## How To Analyse The Synthaxe\n\n![image](images/1.png)\n\n## Creating The List Of Sequences\n\n![image](images/7.png)\n\n## Complete Analysis Corpus\n\n![image](images/8.png)\n\n## Padding Sequences\n\n![image](images/9.png)\n\n## Result Of Padding  Sequence \n\n![image](images/10.png)\n\n## Personnalize Padding\n\n![image](images/11.png)\n\n## Sarcasm in News Headlines Dataset by Rishabh Misra\n\n[https://rishabhmisra.github.io/publications/](https://rishabhmisra.github.io/publications/)\n\n## How To Load Sarcasm Dataset\n\n![image](images/12.png)\n\n## How To Analysis Sarcasm Dataset\n\n![image](images/13.png)\n\n## Sarcasm Detection\n\n* [https://www.kaggle.com/datasets/rmisra/news-headlines-dataset-for-sarcasm-detection](https://www.kaggle.com/datasets/rmisra/news-headlines-dataset-for-sarcasm-detection)\n\n## Build-in Dataset In Tensorflow\n\n![image](images/14.png)\n\n## Dataset\n\n![image](images/15.png)\n\n## Verify Tensorflow Version\n![image](images/16.png)\n\n## Import Tensorflow Dataset\n\n![image](images/17.png)\n\n## Split data\n\n![image](images/18.png)\n\n![image](images/19.png)\n\n![image](images/20.png)\n\n![image](images/21.png)\n\n## Tokenizer\n\n![image](images/22.png)\n\n## Model\n\n![image](images/23.png)\n\nOR\n\n![image](images/24.png)\n\n![image](images/25.png)\n\n## Training Model\n\n![image](images/26.png)\n\n## Expect Layer\n\n![image](images/27.png)\n\n## Reverse Word Index\n\n![image](images/28.png)\n\n## Vecteor In Embedded Data\n\n![image](images/29.png)\n\n## Download In Colab\n\n![image](images/30.png)\n\n![image](images/30.png)\n\n## Model For Sarcasm Dataset\n\n### Importation of Tokenizer And Pad_sequence\n\n![image](images/31.png)\n\n### Hyper Parameters\n\n![image](images/32.png)\n\n### Download Sarcasm Dataset\n\n![image](images/33.png)\n\n### Loading Sarcasm Dataset\n\n![image](images/34.png)\n\n### Building a classifier for the sarcasm dataset\n\n![image](images/35.png)\n\n### Sequence Dataset\n\n![image](images/36.png)\n\n### Create A Model\n\n![image](images/37.png)\n\n### Summarization Of Model\n\n![image](images/38.png)\n\n### Training The Model\n\n![image](images/39.png)\n\n### Plotting The Result Of Training\n\n![image](images/40.png)\n\n![image](images/41.png)\n\n## TensorFlow datasets\n\n* [https://github.com/tensorflow/datasets/tree/master/docs/catalog](https://github.com/tensorflow/datasets/tree/master/docs/catalog)\n\n* [https://www.tensorflow.org/datasets/catalog/overview](https://www.tensorflow.org/datasets/catalog/overview)\n\n## Subwords text encoder\n\n* [https://www.tensorflow.org/datasets/api_docs/python/tfds/deprecated/text/SubwordTextEncoder](https://www.tensorflow.org/datasets/api_docs/python/tfds/deprecated/text/SubwordTextEncoder)\n\n## Diving into the code: Encode And Decode\n\n![image](images/42.png)\n\n![image](images/43.png)\n\n## Classify Sub Word\n\n![image](images/44.png)\n\n![image](images/45.png)\n\n![image](images/46.png)\n\n\n## RNN\n\nThe neural Network is kind a function that we can a data and label it give a rules\n\n![image](images/47.png)\n\n![image](images/48.png)\n\n![image](images/49.png)\n\n## How RNN Work\n\n![image](images/52.png)\n\n## Visualize A Sequence\n\n![image](images/50.png)\n\n![image](images/51.png)\n\n## More About RNN\n\n* [https://www.coursera.org/lecture/nlp-sequence-models/deep-rnns-ehs0S](https://www.coursera.org/lecture/nlp-sequence-models/deep-rnns-ehs0S)\n\n## How To Understang The Context Of Word\n\n![image](images/53.png)\n\n## Uni Directional Cell State\n\n![image](images/54.png)\n\n## Bi Directional Cell State\n\n![image](images/55.png)\n\n## How To Implement LSTM in Tensorflow\n\n![image](images/56.png)\n\n## How To Stack LSTM\n\n![image](images/57.png)\n\n\n## More About LSTMs\n\n* [https://www.coursera.org/lecture/nlp-sequence-models/long-short-term-memory-lstm-KXoay](https://www.coursera.org/lecture/nlp-sequence-models/long-short-term-memory-lstm-KXoay)\n\n\n## Generation A New Text Process\n\n![image](images/58.png)\n\n### Preparing the training data\n\n![image](images/59.png)\n\n![image](images/60.png)\n\n![image](images/61.png)\n\n![image](images/62.png)\n\n![image](images/63.png)\n\n![image](images/64.png)\n\n![image](images/65.png)\n\n### More on the training data\n\n![image](images/66.png)\n\n![image](images/67.png)\n\n![image](images/68.png)\n\n### Finding what the next word should be\n\n![image](images/69.png)\n\n### Example of Text Generated\n\n![image](images/70.png)\n\n### Use Bidirectional LSTM\n\n![image](images/71.png)\n\n### Example After Training With Bidirectional LSTM\n\n![image](images/72.png)\n\n### Predicting a word\n\n![image](images/73.png)\n\n* Tokenize the word to predicting\n  \n ![image](images/74.png)\n\n ![image](images/75.png)\n\n* Padded A Sequence\n\n![image](images/76.png)\n\n![image](images/77.png)\n\n* Passed To Model For Prediction\n  \n![image](images/78.png)\n\n* Reverse Look out\n\n![image](images/79.png)\n\n* Generation By Doing Ten Time\n\n![image](images/80.png)\n\n* Result\n\n![iamge](images/81.png)\n\n### Download A Corpus\n\n![image](images/82.png)\n\n### Looking into the code\n\n![image](images/83.png)\n\n![iamge](images/84.png)\n\n## Userful Link\n\n* [https://www.tensorflow.org/api_docs/python/tf/keras/preprocessing/text/Tokenizer](https://www.tensorflow.org/api_docs/python/tf/keras/preprocessing/text/Tokenizer)\n  \n* [https://ai.stanford.edu/~amaas/data/sentiment/](https://ai.stanford.edu/~amaas/data/sentiment/)\n\n* [https://github.com/tensorflow/datasets/tree/master/docs/catalog](https://github.com/tensorflow/datasets/tree/master/docs/catalog) \n\n* [https://www.tensorflow.org/datasets/catalog/overview](https://www.tensorflow.org/datasets/catalog/overview)\n\n* [https://www.tensorflow.org/text/tutorials/text_generation](https://www.tensorflow.org/text/tutorials/text_generation)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcamara94%2Fnatural-language-processing-tensorflow","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcamara94%2Fnatural-language-processing-tensorflow","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcamara94%2Fnatural-language-processing-tensorflow/lists"}